diff --git a/audio/ptts/tts_aishell1_S0057_BAC009S0057W0130.wav b/audio/ptts/tts_aishell1_S0057_BAC009S0057W0130.wav deleted file mode 100644 index 091812d..0000000 Binary files a/audio/ptts/tts_aishell1_S0057_BAC009S0057W0130.wav and /dev/null differ diff --git a/audio/ptts/tts_aishell2_IC0739W0334.wav b/audio/ptts/tts_aishell2_IC0739W0334.wav deleted file mode 100644 index e4ed5dd..0000000 Binary files a/audio/ptts/tts_aishell2_IC0739W0334.wav and /dev/null differ diff --git a/audio/ptts/tts_libritts_2104_78240_000016_000000.wav b/audio/ptts/tts_libritts_2104_78240_000016_000000.wav deleted file mode 100644 index d852f37..0000000 Binary files a/audio/ptts/tts_libritts_2104_78240_000016_000000.wav and /dev/null differ diff --git a/audio/ptts/tts_libritts_4243_187023_000009_000001.wav b/audio/ptts/tts_libritts_4243_187023_000009_000001.wav deleted file mode 100644 index 60f12d1..0000000 Binary files a/audio/ptts/tts_libritts_4243_187023_000009_000001.wav and /dev/null differ diff --git a/audio/quantized/audiodec/high_tkr/1089-134686-0014.wav b/audio/quantized/audiodec/high_tkr/1089-134686-0014.wav deleted file mode 100644 index 79bed62..0000000 Binary files a/audio/quantized/audiodec/high_tkr/1089-134686-0014.wav and /dev/null differ diff --git a/audio/quantized/audiodec/high_tkr/1320-122617-0000.wav b/audio/quantized/audiodec/high_tkr/1320-122617-0000.wav deleted file mode 100644 index eda7045..0000000 Binary files a/audio/quantized/audiodec/high_tkr/1320-122617-0000.wav and /dev/null differ diff --git a/audio/quantized/audiodec/high_tkr/1580-141083-0040.wav b/audio/quantized/audiodec/high_tkr/1580-141083-0040.wav deleted file mode 100644 index 9f318ee..0000000 Binary files a/audio/quantized/audiodec/high_tkr/1580-141083-0040.wav and /dev/null differ diff --git a/audio/quantized/audiodec/high_tkr/1995-1826-0002.wav b/audio/quantized/audiodec/high_tkr/1995-1826-0002.wav deleted file mode 100644 index 97d9d12..0000000 Binary files a/audio/quantized/audiodec/high_tkr/1995-1826-0002.wav and /dev/null differ diff --git a/audio/quantized/audiodec/high_tkr/BAC009S0765W0344.wav b/audio/quantized/audiodec/high_tkr/BAC009S0765W0344.wav deleted file mode 100644 index 9ff5c2e..0000000 Binary files a/audio/quantized/audiodec/high_tkr/BAC009S0765W0344.wav and /dev/null differ diff --git a/audio/quantized/audiodec/high_tkr/BAC009S0769W0165.wav b/audio/quantized/audiodec/high_tkr/BAC009S0769W0165.wav deleted file mode 100644 index 82ebe52..0000000 Binary files a/audio/quantized/audiodec/high_tkr/BAC009S0769W0165.wav and /dev/null differ diff --git a/audio/quantized/audiodec/high_tkr/BAC009S0915W0395.wav b/audio/quantized/audiodec/high_tkr/BAC009S0915W0395.wav deleted file mode 100644 index e26408a..0000000 Binary files a/audio/quantized/audiodec/high_tkr/BAC009S0915W0395.wav and /dev/null differ diff --git a/audio/quantized/audiodec/high_tkr/BAC009S0916W0281.wav b/audio/quantized/audiodec/high_tkr/BAC009S0916W0281.wav deleted file mode 100644 index 6d467f6..0000000 Binary files a/audio/quantized/audiodec/high_tkr/BAC009S0916W0281.wav and /dev/null differ diff --git a/audio/quantized/audiodec/low_tkr/1089-134686-0014.wav b/audio/quantized/audiodec/low_tkr/1089-134686-0014.wav deleted file mode 100644 index b3ac0f8..0000000 Binary files a/audio/quantized/audiodec/low_tkr/1089-134686-0014.wav and /dev/null differ diff --git a/audio/quantized/audiodec/low_tkr/1320-122617-0000.wav b/audio/quantized/audiodec/low_tkr/1320-122617-0000.wav deleted file mode 100644 index 1c65c62..0000000 Binary files a/audio/quantized/audiodec/low_tkr/1320-122617-0000.wav and /dev/null differ diff --git a/audio/quantized/audiodec/low_tkr/1580-141083-0040.wav b/audio/quantized/audiodec/low_tkr/1580-141083-0040.wav deleted file mode 100644 index 424cfe4..0000000 Binary files a/audio/quantized/audiodec/low_tkr/1580-141083-0040.wav and /dev/null differ diff --git a/audio/quantized/audiodec/low_tkr/1995-1826-0002.wav b/audio/quantized/audiodec/low_tkr/1995-1826-0002.wav deleted file mode 100644 index cb8b2ed..0000000 Binary files a/audio/quantized/audiodec/low_tkr/1995-1826-0002.wav and /dev/null differ diff --git a/audio/quantized/audiodec/low_tkr/BAC009S0765W0344.wav b/audio/quantized/audiodec/low_tkr/BAC009S0765W0344.wav deleted file mode 100644 index 6eb3d8c..0000000 Binary files a/audio/quantized/audiodec/low_tkr/BAC009S0765W0344.wav and /dev/null differ diff --git a/audio/quantized/audiodec/low_tkr/BAC009S0769W0165.wav b/audio/quantized/audiodec/low_tkr/BAC009S0769W0165.wav deleted file mode 100644 index 6f32b33..0000000 Binary files a/audio/quantized/audiodec/low_tkr/BAC009S0769W0165.wav and /dev/null differ diff --git a/audio/quantized/audiodec/low_tkr/BAC009S0915W0395.wav b/audio/quantized/audiodec/low_tkr/BAC009S0915W0395.wav deleted file mode 100644 index 73cd0ae..0000000 Binary files a/audio/quantized/audiodec/low_tkr/BAC009S0915W0395.wav and /dev/null differ diff --git a/audio/quantized/audiodec/low_tkr/BAC009S0916W0281.wav b/audio/quantized/audiodec/low_tkr/BAC009S0916W0281.wav deleted file mode 100644 index b68109f..0000000 Binary files a/audio/quantized/audiodec/low_tkr/BAC009S0916W0281.wav and /dev/null differ diff --git a/audio/quantized/clean/1089-134686-0014.wav b/audio/quantized/clean/1089-134686-0014.wav deleted file mode 100644 index e9c4cc2..0000000 Binary files a/audio/quantized/clean/1089-134686-0014.wav and /dev/null differ diff --git a/audio/quantized/clean/1320-122617-0000.wav b/audio/quantized/clean/1320-122617-0000.wav deleted file mode 100644 index d2c3dc7..0000000 Binary files a/audio/quantized/clean/1320-122617-0000.wav and /dev/null differ diff --git a/audio/quantized/clean/1580-141083-0040.wav b/audio/quantized/clean/1580-141083-0040.wav deleted file mode 100644 index cb656d6..0000000 Binary files a/audio/quantized/clean/1580-141083-0040.wav and /dev/null differ diff --git a/audio/quantized/clean/1995-1826-0002.wav b/audio/quantized/clean/1995-1826-0002.wav deleted file mode 100644 index b78530b..0000000 Binary files a/audio/quantized/clean/1995-1826-0002.wav and /dev/null differ diff --git a/audio/quantized/clean/BAC009S0765W0344.wav b/audio/quantized/clean/BAC009S0765W0344.wav deleted file mode 100644 index 11b9159..0000000 Binary files a/audio/quantized/clean/BAC009S0765W0344.wav and /dev/null differ diff --git a/audio/quantized/clean/BAC009S0769W0165.wav b/audio/quantized/clean/BAC009S0769W0165.wav deleted file mode 100644 index c967ae9..0000000 Binary files a/audio/quantized/clean/BAC009S0769W0165.wav and /dev/null differ diff --git a/audio/quantized/clean/BAC009S0915W0395.wav b/audio/quantized/clean/BAC009S0915W0395.wav deleted file mode 100644 index fd47eec..0000000 Binary files a/audio/quantized/clean/BAC009S0915W0395.wav and /dev/null differ diff --git a/audio/quantized/clean/BAC009S0916W0281.wav b/audio/quantized/clean/BAC009S0916W0281.wav deleted file mode 100644 index 913c648..0000000 Binary files a/audio/quantized/clean/BAC009S0916W0281.wav and /dev/null differ diff --git a/audio/quantized/dac/high_tkr/1089-134686-0014.wav b/audio/quantized/dac/high_tkr/1089-134686-0014.wav deleted file mode 100644 index 2cbd243..0000000 Binary files a/audio/quantized/dac/high_tkr/1089-134686-0014.wav and /dev/null differ diff --git a/audio/quantized/dac/high_tkr/1320-122617-0000.wav b/audio/quantized/dac/high_tkr/1320-122617-0000.wav deleted file mode 100644 index 833822b..0000000 Binary files a/audio/quantized/dac/high_tkr/1320-122617-0000.wav and /dev/null differ diff --git a/audio/quantized/dac/high_tkr/1580-141083-0040.wav b/audio/quantized/dac/high_tkr/1580-141083-0040.wav deleted file mode 100644 index 2acccfe..0000000 Binary files a/audio/quantized/dac/high_tkr/1580-141083-0040.wav and /dev/null differ diff --git a/audio/quantized/dac/high_tkr/1995-1826-0002.wav b/audio/quantized/dac/high_tkr/1995-1826-0002.wav deleted file mode 100644 index cf95147..0000000 Binary files a/audio/quantized/dac/high_tkr/1995-1826-0002.wav and /dev/null differ diff --git a/audio/quantized/dac/high_tkr/BAC009S0765W0344.wav b/audio/quantized/dac/high_tkr/BAC009S0765W0344.wav deleted file mode 100644 index da7a6ed..0000000 Binary files a/audio/quantized/dac/high_tkr/BAC009S0765W0344.wav and /dev/null differ diff --git a/audio/quantized/dac/high_tkr/BAC009S0769W0165.wav b/audio/quantized/dac/high_tkr/BAC009S0769W0165.wav deleted file mode 100644 index fc293e7..0000000 Binary files a/audio/quantized/dac/high_tkr/BAC009S0769W0165.wav and /dev/null differ diff --git a/audio/quantized/dac/high_tkr/BAC009S0915W0395.wav b/audio/quantized/dac/high_tkr/BAC009S0915W0395.wav deleted file mode 100644 index e899e57..0000000 Binary files a/audio/quantized/dac/high_tkr/BAC009S0915W0395.wav and /dev/null differ diff --git a/audio/quantized/dac/high_tkr/BAC009S0916W0281.wav b/audio/quantized/dac/high_tkr/BAC009S0916W0281.wav deleted file mode 100644 index 6b2f189..0000000 Binary files a/audio/quantized/dac/high_tkr/BAC009S0916W0281.wav and /dev/null differ diff --git a/audio/quantized/dac/low_tkr/1089-134686-0014.wav b/audio/quantized/dac/low_tkr/1089-134686-0014.wav deleted file mode 100644 index 8bda121..0000000 Binary files a/audio/quantized/dac/low_tkr/1089-134686-0014.wav and /dev/null differ diff --git a/audio/quantized/dac/low_tkr/1320-122617-0000.wav b/audio/quantized/dac/low_tkr/1320-122617-0000.wav deleted file mode 100644 index 4d9a14d..0000000 Binary files a/audio/quantized/dac/low_tkr/1320-122617-0000.wav and /dev/null differ diff --git a/audio/quantized/dac/low_tkr/1580-141083-0040.wav b/audio/quantized/dac/low_tkr/1580-141083-0040.wav deleted file mode 100644 index 1abfd06..0000000 Binary files a/audio/quantized/dac/low_tkr/1580-141083-0040.wav and /dev/null differ diff --git a/audio/quantized/dac/low_tkr/1995-1826-0002.wav b/audio/quantized/dac/low_tkr/1995-1826-0002.wav deleted file mode 100644 index c64b08a..0000000 Binary files a/audio/quantized/dac/low_tkr/1995-1826-0002.wav and /dev/null differ diff --git a/audio/quantized/dac/low_tkr/BAC009S0765W0344.wav b/audio/quantized/dac/low_tkr/BAC009S0765W0344.wav deleted file mode 100644 index 76806a0..0000000 Binary files a/audio/quantized/dac/low_tkr/BAC009S0765W0344.wav and /dev/null differ diff --git a/audio/quantized/dac/low_tkr/BAC009S0769W0165.wav b/audio/quantized/dac/low_tkr/BAC009S0769W0165.wav deleted file mode 100644 index 8511178..0000000 Binary files a/audio/quantized/dac/low_tkr/BAC009S0769W0165.wav and /dev/null differ diff --git a/audio/quantized/dac/low_tkr/BAC009S0915W0395.wav b/audio/quantized/dac/low_tkr/BAC009S0915W0395.wav deleted file mode 100644 index 6751137..0000000 Binary files a/audio/quantized/dac/low_tkr/BAC009S0915W0395.wav and /dev/null differ diff --git a/audio/quantized/dac/low_tkr/BAC009S0916W0281.wav b/audio/quantized/dac/low_tkr/BAC009S0916W0281.wav deleted file mode 100644 index 7e223e3..0000000 Binary files a/audio/quantized/dac/low_tkr/BAC009S0916W0281.wav and /dev/null differ diff --git a/audio/quantized/encodec/high_tkr/1089-134686-0014.wav b/audio/quantized/encodec/high_tkr/1089-134686-0014.wav deleted file mode 100644 index 01bb71c..0000000 Binary files a/audio/quantized/encodec/high_tkr/1089-134686-0014.wav and /dev/null differ diff --git a/audio/quantized/encodec/high_tkr/1320-122617-0000.wav b/audio/quantized/encodec/high_tkr/1320-122617-0000.wav deleted file mode 100644 index dfcb611..0000000 Binary files a/audio/quantized/encodec/high_tkr/1320-122617-0000.wav and /dev/null differ diff --git a/audio/quantized/encodec/high_tkr/1580-141083-0040.wav b/audio/quantized/encodec/high_tkr/1580-141083-0040.wav deleted file mode 100644 index 8afdebd..0000000 Binary files a/audio/quantized/encodec/high_tkr/1580-141083-0040.wav and /dev/null differ diff --git a/audio/quantized/encodec/high_tkr/1995-1826-0002.wav b/audio/quantized/encodec/high_tkr/1995-1826-0002.wav deleted file mode 100644 index 6320e2d..0000000 Binary files a/audio/quantized/encodec/high_tkr/1995-1826-0002.wav and /dev/null differ diff --git a/audio/quantized/encodec/high_tkr/BAC009S0765W0344.wav b/audio/quantized/encodec/high_tkr/BAC009S0765W0344.wav deleted file mode 100644 index df4ee53..0000000 Binary files a/audio/quantized/encodec/high_tkr/BAC009S0765W0344.wav and /dev/null differ diff --git a/audio/quantized/encodec/high_tkr/BAC009S0769W0165.wav b/audio/quantized/encodec/high_tkr/BAC009S0769W0165.wav deleted file mode 100644 index 7bd782b..0000000 Binary files a/audio/quantized/encodec/high_tkr/BAC009S0769W0165.wav and /dev/null differ diff --git a/audio/quantized/encodec/high_tkr/BAC009S0915W0395.wav b/audio/quantized/encodec/high_tkr/BAC009S0915W0395.wav deleted file mode 100644 index 87dc864..0000000 Binary files a/audio/quantized/encodec/high_tkr/BAC009S0915W0395.wav and /dev/null differ diff --git a/audio/quantized/encodec/high_tkr/BAC009S0916W0281.wav b/audio/quantized/encodec/high_tkr/BAC009S0916W0281.wav deleted file mode 100644 index ab04b7a..0000000 Binary files a/audio/quantized/encodec/high_tkr/BAC009S0916W0281.wav and /dev/null differ diff --git a/audio/quantized/encodec/low_tkr/1089-134686-0014.wav b/audio/quantized/encodec/low_tkr/1089-134686-0014.wav deleted file mode 100644 index c3b584f..0000000 Binary files a/audio/quantized/encodec/low_tkr/1089-134686-0014.wav and /dev/null differ diff --git a/audio/quantized/encodec/low_tkr/1320-122617-0000.wav b/audio/quantized/encodec/low_tkr/1320-122617-0000.wav deleted file mode 100644 index ebb1a51..0000000 Binary files a/audio/quantized/encodec/low_tkr/1320-122617-0000.wav and /dev/null differ diff --git a/audio/quantized/encodec/low_tkr/1580-141083-0040.wav b/audio/quantized/encodec/low_tkr/1580-141083-0040.wav deleted file mode 100644 index 914d872..0000000 Binary files a/audio/quantized/encodec/low_tkr/1580-141083-0040.wav and /dev/null differ diff --git a/audio/quantized/encodec/low_tkr/1995-1826-0002.wav b/audio/quantized/encodec/low_tkr/1995-1826-0002.wav deleted file mode 100644 index 65bda3c..0000000 Binary files a/audio/quantized/encodec/low_tkr/1995-1826-0002.wav and /dev/null differ diff --git a/audio/quantized/encodec/low_tkr/BAC009S0765W0344.wav b/audio/quantized/encodec/low_tkr/BAC009S0765W0344.wav deleted file mode 100644 index 2edab69..0000000 Binary files a/audio/quantized/encodec/low_tkr/BAC009S0765W0344.wav and /dev/null differ diff --git a/audio/quantized/encodec/low_tkr/BAC009S0769W0165.wav b/audio/quantized/encodec/low_tkr/BAC009S0769W0165.wav deleted file mode 100644 index 0a62765..0000000 Binary files a/audio/quantized/encodec/low_tkr/BAC009S0769W0165.wav and /dev/null differ diff --git a/audio/quantized/encodec/low_tkr/BAC009S0915W0395.wav b/audio/quantized/encodec/low_tkr/BAC009S0915W0395.wav deleted file mode 100644 index 6aa6ba6..0000000 Binary files a/audio/quantized/encodec/low_tkr/BAC009S0915W0395.wav and /dev/null differ diff --git a/audio/quantized/encodec/low_tkr/BAC009S0916W0281.wav b/audio/quantized/encodec/low_tkr/BAC009S0916W0281.wav deleted file mode 100644 index b7b9bb2..0000000 Binary files a/audio/quantized/encodec/low_tkr/BAC009S0916W0281.wav and /dev/null differ diff --git a/audio/quantized/funcodec/high_tkr/1089-134686-0014.wav b/audio/quantized/funcodec/high_tkr/1089-134686-0014.wav deleted file mode 100644 index 8d0d22b..0000000 Binary files a/audio/quantized/funcodec/high_tkr/1089-134686-0014.wav and /dev/null differ diff --git a/audio/quantized/funcodec/high_tkr/1320-122617-0000.wav b/audio/quantized/funcodec/high_tkr/1320-122617-0000.wav deleted file mode 100644 index 92c321a..0000000 Binary files a/audio/quantized/funcodec/high_tkr/1320-122617-0000.wav and /dev/null differ diff --git a/audio/quantized/funcodec/high_tkr/1580-141083-0040.wav b/audio/quantized/funcodec/high_tkr/1580-141083-0040.wav deleted file mode 100644 index 617d236..0000000 Binary files a/audio/quantized/funcodec/high_tkr/1580-141083-0040.wav and /dev/null differ diff --git a/audio/quantized/funcodec/high_tkr/1995-1826-0002.wav b/audio/quantized/funcodec/high_tkr/1995-1826-0002.wav deleted file mode 100644 index 1aee00c..0000000 Binary files a/audio/quantized/funcodec/high_tkr/1995-1826-0002.wav and /dev/null differ diff --git a/audio/quantized/funcodec/high_tkr/BAC009S0765W0344.wav b/audio/quantized/funcodec/high_tkr/BAC009S0765W0344.wav deleted file mode 100644 index 4f04d10..0000000 Binary files a/audio/quantized/funcodec/high_tkr/BAC009S0765W0344.wav and /dev/null differ diff --git a/audio/quantized/funcodec/high_tkr/BAC009S0769W0165.wav b/audio/quantized/funcodec/high_tkr/BAC009S0769W0165.wav deleted file mode 100644 index b8812ac..0000000 Binary files a/audio/quantized/funcodec/high_tkr/BAC009S0769W0165.wav and /dev/null differ diff --git a/audio/quantized/funcodec/high_tkr/BAC009S0915W0395.wav b/audio/quantized/funcodec/high_tkr/BAC009S0915W0395.wav deleted file mode 100644 index 388a751..0000000 Binary files a/audio/quantized/funcodec/high_tkr/BAC009S0915W0395.wav and /dev/null differ diff --git a/audio/quantized/funcodec/high_tkr/BAC009S0916W0281.wav b/audio/quantized/funcodec/high_tkr/BAC009S0916W0281.wav deleted file mode 100644 index 051c2df..0000000 Binary files a/audio/quantized/funcodec/high_tkr/BAC009S0916W0281.wav and /dev/null differ diff --git a/audio/quantized/funcodec/low_tkr/1089-134686-0014.wav b/audio/quantized/funcodec/low_tkr/1089-134686-0014.wav deleted file mode 100644 index e60f480..0000000 Binary files a/audio/quantized/funcodec/low_tkr/1089-134686-0014.wav and /dev/null differ diff --git a/audio/quantized/funcodec/low_tkr/1320-122617-0000.wav b/audio/quantized/funcodec/low_tkr/1320-122617-0000.wav deleted file mode 100644 index a0e760a..0000000 Binary files a/audio/quantized/funcodec/low_tkr/1320-122617-0000.wav and /dev/null differ diff --git a/audio/quantized/funcodec/low_tkr/1580-141083-0040.wav b/audio/quantized/funcodec/low_tkr/1580-141083-0040.wav deleted file mode 100644 index ad34ea5..0000000 Binary files a/audio/quantized/funcodec/low_tkr/1580-141083-0040.wav and /dev/null differ diff --git a/audio/quantized/funcodec/low_tkr/1995-1826-0002.wav b/audio/quantized/funcodec/low_tkr/1995-1826-0002.wav deleted file mode 100644 index cd97a09..0000000 Binary files a/audio/quantized/funcodec/low_tkr/1995-1826-0002.wav and /dev/null differ diff --git a/audio/quantized/funcodec/low_tkr/BAC009S0765W0344.wav b/audio/quantized/funcodec/low_tkr/BAC009S0765W0344.wav deleted file mode 100644 index 3feaf93..0000000 Binary files a/audio/quantized/funcodec/low_tkr/BAC009S0765W0344.wav and /dev/null differ diff --git a/audio/quantized/funcodec/low_tkr/BAC009S0769W0165.wav b/audio/quantized/funcodec/low_tkr/BAC009S0769W0165.wav deleted file mode 100644 index 2c04744..0000000 Binary files a/audio/quantized/funcodec/low_tkr/BAC009S0769W0165.wav and /dev/null differ diff --git a/audio/quantized/funcodec/low_tkr/BAC009S0915W0395.wav b/audio/quantized/funcodec/low_tkr/BAC009S0915W0395.wav deleted file mode 100644 index c91c15b..0000000 Binary files a/audio/quantized/funcodec/low_tkr/BAC009S0915W0395.wav and /dev/null differ diff --git a/audio/quantized/funcodec/low_tkr/BAC009S0916W0281.wav b/audio/quantized/funcodec/low_tkr/BAC009S0916W0281.wav deleted file mode 100644 index 302f85e..0000000 Binary files a/audio/quantized/funcodec/low_tkr/BAC009S0916W0281.wav and /dev/null differ diff --git a/audio/s2tt_samples/example_en2zh_1.mp3 b/audio/s2tt_samples/example_en2zh_1.mp3 new file mode 100644 index 0000000..a90726b Binary files /dev/null and b/audio/s2tt_samples/example_en2zh_1.mp3 differ diff --git a/audio/s2tt_samples/example_en2zh_2.mp3 b/audio/s2tt_samples/example_en2zh_2.mp3 new file mode 100644 index 0000000..50672c3 Binary files /dev/null and b/audio/s2tt_samples/example_en2zh_2.mp3 differ diff --git a/audio/s2tt_samples/example_en2zh_3.mp3 b/audio/s2tt_samples/example_en2zh_3.mp3 new file mode 100644 index 0000000..8bfc3c5 Binary files /dev/null and b/audio/s2tt_samples/example_en2zh_3.mp3 differ diff --git a/audio/s2tt_samples/example_zh2en_1.wav b/audio/s2tt_samples/example_zh2en_1.wav new file mode 100644 index 0000000..ba6200f Binary files /dev/null and b/audio/s2tt_samples/example_zh2en_1.wav differ diff --git a/audio/s2tt_samples/example_zh2en_2.wav b/audio/s2tt_samples/example_zh2en_2.wav new file mode 100644 index 0000000..4103ac4 Binary files /dev/null and b/audio/s2tt_samples/example_zh2en_2.wav differ diff --git a/audio/s2tt_samples/example_zh2en_3.wav b/audio/s2tt_samples/example_zh2en_3.wav new file mode 100644 index 0000000..0fba827 Binary files /dev/null and b/audio/s2tt_samples/example_zh2en_3.wav differ diff --git a/audio/s2tt_samples/mt_results.txt b/audio/s2tt_samples/mt_results.txt new file mode 100644 index 0000000..c516455 --- /dev/null +++ b/audio/s2tt_samples/mt_results.txt @@ -0,0 +1,4 @@ +example_zh2en_1 青海三江源地区是我国乃至亚洲重要的生态屏障和水源涵养区,而青海湖是控制西部荒漠化向东蔓延的天然屏障和生态功能区。 Qinghai Sanjiangyuan area is an important ecological barrier and water nourishing area in China and Asia, while Qinghai Lake is a natural barrier and ecological function zone to control the eastward spread of western desertification. +example_zh2en_2 世界饮料创新奖表彰了全球饮料行业新老品牌今年最具雄心的新产品和新发展。 World Beverage Innovation Awards recognize the most ambitious new products and developments of new and established brands in the global beverage industry this year. +example_en2zh_1 If you have any questions, please feel free to contact us through the eBay emailing system. 如果您有任何疑问,请随时通过eBay电子邮件系统与我们联系。 +example_en2zh_2 Our aim is to offer our customers the best service possible. 我们的目标是为客户提供最好的服务。 \ No newline at end of file diff --git a/audio/s2tt_samples/results.txt b/audio/s2tt_samples/results.txt new file mode 100644 index 0000000..2e67f1d --- /dev/null +++ b/audio/s2tt_samples/results.txt @@ -0,0 +1,6 @@ +example_zh2en_1 But not all of them can be successful in the market. +example_zh2en_2 Welcome to the advanced course on the UNIT dialogue system. +example_zh2en_3 Then, upload the AR content package to the AR content platform. +example_en2zh_1 但他似乎没有意识到任何危险。 +example_en2zh_2 我想预订一间靠近我们公寓的酒吧。 +example_en2zh_3 主要是那些努力实现自己命运的人的心。 diff --git a/audio/se_samples/aishell.scp b/audio/se_samples/aishell.scp new file mode 100644 index 0000000..2ab3855 --- /dev/null +++ b/audio/se_samples/aishell.scp @@ -0,0 +1,10 @@ +se_aishell_BAC009S0768W0436-FSD50K_eval_audio_16k_114454-2.0.wav 3.1233 +se_aishell_BAC009S0770W0460-musan_noise-free-sound-0731-2.0.wav 3.2174 +se_aishell_BAC009S0915W0347-FSD50K_eval_audio_16k_234044-5.0.wav 3.5258 +se_aishell_BAC009S0766W0130-FSD50K_eval_audio_16k_408627-5.0.wav 3.1213 +se_aishell_BAC009S0915W0432-MagnaTagATune_solace-the_gathering_season-10-hujayni-88-117-7.0.wav 3.2447 +se_aishell_BAC009S0764W0445-FSD50K_eval_audio_16k_404398-7.0.wav 3.1888 +se_aishell_BAC009S0901W0447-FSD50K_eval_audio_16k_235964-10.0.wav 3.2347 +se_aishell_BAC009S0901W0443-MagnaTagATune_rapoon-the_kirghiz_light__cd_1-09-meridia_closes-233-262-10.0.wav 3.4681 +se_aishell_BAC009S0916W0211-FSD50K_eval_audio_16k_360680-12.0.wav 3.0523 +se_aishell_BAC009S0901W0350-FSD50K_eval_audio_16k_67307-12.0.wav 4.3163 diff --git a/audio/se_samples/clean/se_aishell_BAC009S0764W0445-FSD50K_eval_audio_16k_404398-7.0.wav b/audio/se_samples/clean/se_aishell_BAC009S0764W0445-FSD50K_eval_audio_16k_404398-7.0.wav new file mode 100644 index 0000000..4732e36 Binary files /dev/null and b/audio/se_samples/clean/se_aishell_BAC009S0764W0445-FSD50K_eval_audio_16k_404398-7.0.wav differ diff --git a/audio/se_samples/clean/se_aishell_BAC009S0766W0130-FSD50K_eval_audio_16k_408627-5.0.wav b/audio/se_samples/clean/se_aishell_BAC009S0766W0130-FSD50K_eval_audio_16k_408627-5.0.wav new file mode 100644 index 0000000..e5d6512 Binary files /dev/null and b/audio/se_samples/clean/se_aishell_BAC009S0766W0130-FSD50K_eval_audio_16k_408627-5.0.wav differ diff --git a/audio/se_samples/clean/se_aishell_BAC009S0768W0436-FSD50K_eval_audio_16k_114454-2.0.wav b/audio/se_samples/clean/se_aishell_BAC009S0768W0436-FSD50K_eval_audio_16k_114454-2.0.wav new file mode 100644 index 0000000..fb98258 Binary files /dev/null and b/audio/se_samples/clean/se_aishell_BAC009S0768W0436-FSD50K_eval_audio_16k_114454-2.0.wav differ diff --git a/audio/se_samples/clean/se_aishell_BAC009S0770W0460-musan_noise-free-sound-0731-2.0.wav b/audio/se_samples/clean/se_aishell_BAC009S0770W0460-musan_noise-free-sound-0731-2.0.wav new file mode 100644 index 0000000..f051359 Binary files /dev/null and b/audio/se_samples/clean/se_aishell_BAC009S0770W0460-musan_noise-free-sound-0731-2.0.wav differ diff --git a/audio/se_samples/clean/se_aishell_BAC009S0901W0350-FSD50K_eval_audio_16k_67307-12.0.wav b/audio/se_samples/clean/se_aishell_BAC009S0901W0350-FSD50K_eval_audio_16k_67307-12.0.wav new file mode 100644 index 0000000..0802d2f Binary files /dev/null and b/audio/se_samples/clean/se_aishell_BAC009S0901W0350-FSD50K_eval_audio_16k_67307-12.0.wav differ diff --git a/audio/se_samples/clean/se_aishell_BAC009S0901W0443-MagnaTagATune_rapoon-the_kirghiz_light__cd_1-09-meridia_closes-233-262-10.0.wav b/audio/se_samples/clean/se_aishell_BAC009S0901W0443-MagnaTagATune_rapoon-the_kirghiz_light__cd_1-09-meridia_closes-233-262-10.0.wav new file mode 100644 index 0000000..ecbea0f Binary files /dev/null and b/audio/se_samples/clean/se_aishell_BAC009S0901W0443-MagnaTagATune_rapoon-the_kirghiz_light__cd_1-09-meridia_closes-233-262-10.0.wav differ diff --git a/audio/se_samples/clean/se_aishell_BAC009S0901W0447-FSD50K_eval_audio_16k_235964-10.0.wav b/audio/se_samples/clean/se_aishell_BAC009S0901W0447-FSD50K_eval_audio_16k_235964-10.0.wav new file mode 100644 index 0000000..39f6b2e Binary files /dev/null and b/audio/se_samples/clean/se_aishell_BAC009S0901W0447-FSD50K_eval_audio_16k_235964-10.0.wav differ diff --git a/audio/se_samples/clean/se_aishell_BAC009S0915W0347-FSD50K_eval_audio_16k_234044-5.0.wav b/audio/se_samples/clean/se_aishell_BAC009S0915W0347-FSD50K_eval_audio_16k_234044-5.0.wav new file mode 100644 index 0000000..a5004f3 Binary files /dev/null and b/audio/se_samples/clean/se_aishell_BAC009S0915W0347-FSD50K_eval_audio_16k_234044-5.0.wav differ diff --git a/audio/se_samples/clean/se_aishell_BAC009S0915W0432-MagnaTagATune_solace-the_gathering_season-10-hujayni-88-117-7.0.wav b/audio/se_samples/clean/se_aishell_BAC009S0915W0432-MagnaTagATune_solace-the_gathering_season-10-hujayni-88-117-7.0.wav new file mode 100644 index 0000000..b81c744 Binary files /dev/null and b/audio/se_samples/clean/se_aishell_BAC009S0915W0432-MagnaTagATune_solace-the_gathering_season-10-hujayni-88-117-7.0.wav differ diff --git a/audio/se_samples/clean/se_aishell_BAC009S0916W0211-FSD50K_eval_audio_16k_360680-12.0.wav b/audio/se_samples/clean/se_aishell_BAC009S0916W0211-FSD50K_eval_audio_16k_360680-12.0.wav new file mode 100644 index 0000000..02dd78e Binary files /dev/null and b/audio/se_samples/clean/se_aishell_BAC009S0916W0211-FSD50K_eval_audio_16k_360680-12.0.wav differ diff --git a/audio/se_samples/clean/se_librispeech_1320-122617-0013-FSD50K_eval_audio_16k_325526-5.0.wav b/audio/se_samples/clean/se_librispeech_1320-122617-0013-FSD50K_eval_audio_16k_325526-5.0.wav new file mode 100644 index 0000000..a2724d3 Binary files /dev/null and b/audio/se_samples/clean/se_librispeech_1320-122617-0013-FSD50K_eval_audio_16k_325526-5.0.wav differ diff --git a/audio/se_samples/clean/se_librispeech_1998-15444-0019-FSD50K_eval_audio_16k_382586-7.0.wav b/audio/se_samples/clean/se_librispeech_1998-15444-0019-FSD50K_eval_audio_16k_382586-7.0.wav new file mode 100644 index 0000000..3d49d9a Binary files /dev/null and b/audio/se_samples/clean/se_librispeech_1998-15444-0019-FSD50K_eval_audio_16k_382586-7.0.wav differ diff --git a/audio/se_samples/clean/se_librispeech_237-134500-0000-FSD50K_eval_audio_16k_403295-10.0.wav b/audio/se_samples/clean/se_librispeech_237-134500-0000-FSD50K_eval_audio_16k_403295-10.0.wav new file mode 100644 index 0000000..c65a413 Binary files /dev/null and b/audio/se_samples/clean/se_librispeech_237-134500-0000-FSD50K_eval_audio_16k_403295-10.0.wav differ diff --git a/audio/se_samples/clean/se_librispeech_2414-159411-0013-FSD50K_eval_audio_16k_164036-12.0.wav b/audio/se_samples/clean/se_librispeech_2414-159411-0013-FSD50K_eval_audio_16k_164036-12.0.wav new file mode 100644 index 0000000..25c81d3 Binary files /dev/null and b/audio/se_samples/clean/se_librispeech_2414-159411-0013-FSD50K_eval_audio_16k_164036-12.0.wav differ diff --git a/audio/se_samples/clean/se_librispeech_260-123440-0011-FSD50K_eval_audio_16k_203808-12.0.wav b/audio/se_samples/clean/se_librispeech_260-123440-0011-FSD50K_eval_audio_16k_203808-12.0.wav new file mode 100644 index 0000000..95f1c67 Binary files /dev/null and b/audio/se_samples/clean/se_librispeech_260-123440-0011-FSD50K_eval_audio_16k_203808-12.0.wav differ diff --git a/audio/se_samples/clean/se_librispeech_3538-142836-0003-FSD50K_eval_audio_16k_176925-10.0.wav b/audio/se_samples/clean/se_librispeech_3538-142836-0003-FSD50K_eval_audio_16k_176925-10.0.wav new file mode 100644 index 0000000..300f01e Binary files /dev/null and b/audio/se_samples/clean/se_librispeech_3538-142836-0003-FSD50K_eval_audio_16k_176925-10.0.wav differ diff --git a/audio/se_samples/clean/se_librispeech_6829-68771-0002-FSD50K_eval_audio_16k_62952-5.0.wav b/audio/se_samples/clean/se_librispeech_6829-68771-0002-FSD50K_eval_audio_16k_62952-5.0.wav new file mode 100644 index 0000000..3dd4da6 Binary files /dev/null and b/audio/se_samples/clean/se_librispeech_6829-68771-0002-FSD50K_eval_audio_16k_62952-5.0.wav differ diff --git a/audio/se_samples/clean/se_librispeech_7105-2330-0027-FSD50K_eval_audio_16k_251931-2.0.wav b/audio/se_samples/clean/se_librispeech_7105-2330-0027-FSD50K_eval_audio_16k_251931-2.0.wav new file mode 100644 index 0000000..a7fa238 Binary files /dev/null and b/audio/se_samples/clean/se_librispeech_7105-2330-0027-FSD50K_eval_audio_16k_251931-2.0.wav differ diff --git a/audio/se_samples/clean/se_librispeech_7975-280085-0005-FSD50K_eval_audio_16k_180338-10.0.wav b/audio/se_samples/clean/se_librispeech_7975-280085-0005-FSD50K_eval_audio_16k_180338-10.0.wav new file mode 100644 index 0000000..18fbf61 Binary files /dev/null and b/audio/se_samples/clean/se_librispeech_7975-280085-0005-FSD50K_eval_audio_16k_180338-10.0.wav differ diff --git a/audio/se_samples/clean/se_librispeech_8188-269290-0023-FSD50K_eval_audio_16k_337937-7.0.wav b/audio/se_samples/clean/se_librispeech_8188-269290-0023-FSD50K_eval_audio_16k_337937-7.0.wav new file mode 100644 index 0000000..7fae7db Binary files /dev/null and b/audio/se_samples/clean/se_librispeech_8188-269290-0023-FSD50K_eval_audio_16k_337937-7.0.wav differ diff --git a/audio/se_samples/enhanced/se_aishell_BAC009S0764W0445-FSD50K_eval_audio_16k_404398-7.0.wav b/audio/se_samples/enhanced/se_aishell_BAC009S0764W0445-FSD50K_eval_audio_16k_404398-7.0.wav new file mode 100644 index 0000000..3e40144 Binary files /dev/null and b/audio/se_samples/enhanced/se_aishell_BAC009S0764W0445-FSD50K_eval_audio_16k_404398-7.0.wav differ diff --git a/audio/se_samples/enhanced/se_aishell_BAC009S0766W0130-FSD50K_eval_audio_16k_408627-5.0.wav b/audio/se_samples/enhanced/se_aishell_BAC009S0766W0130-FSD50K_eval_audio_16k_408627-5.0.wav new file mode 100644 index 0000000..7a95fab Binary files /dev/null and b/audio/se_samples/enhanced/se_aishell_BAC009S0766W0130-FSD50K_eval_audio_16k_408627-5.0.wav differ diff --git a/audio/se_samples/enhanced/se_aishell_BAC009S0768W0436-FSD50K_eval_audio_16k_114454-2.0.wav b/audio/se_samples/enhanced/se_aishell_BAC009S0768W0436-FSD50K_eval_audio_16k_114454-2.0.wav new file mode 100644 index 0000000..cc828e3 Binary files /dev/null and b/audio/se_samples/enhanced/se_aishell_BAC009S0768W0436-FSD50K_eval_audio_16k_114454-2.0.wav differ diff --git a/audio/se_samples/enhanced/se_aishell_BAC009S0770W0460-musan_noise-free-sound-0731-2.0.wav b/audio/se_samples/enhanced/se_aishell_BAC009S0770W0460-musan_noise-free-sound-0731-2.0.wav new file mode 100644 index 0000000..76ccce1 Binary files /dev/null and b/audio/se_samples/enhanced/se_aishell_BAC009S0770W0460-musan_noise-free-sound-0731-2.0.wav differ diff --git a/audio/se_samples/enhanced/se_aishell_BAC009S0901W0350-FSD50K_eval_audio_16k_67307-12.0.wav b/audio/se_samples/enhanced/se_aishell_BAC009S0901W0350-FSD50K_eval_audio_16k_67307-12.0.wav new file mode 100644 index 0000000..3c58f8c Binary files /dev/null and b/audio/se_samples/enhanced/se_aishell_BAC009S0901W0350-FSD50K_eval_audio_16k_67307-12.0.wav differ diff --git a/audio/se_samples/enhanced/se_aishell_BAC009S0901W0443-MagnaTagATune_rapoon-the_kirghiz_light__cd_1-09-meridia_closes-233-262-10.0.wav b/audio/se_samples/enhanced/se_aishell_BAC009S0901W0443-MagnaTagATune_rapoon-the_kirghiz_light__cd_1-09-meridia_closes-233-262-10.0.wav new file mode 100644 index 0000000..9dae820 Binary files /dev/null and b/audio/se_samples/enhanced/se_aishell_BAC009S0901W0443-MagnaTagATune_rapoon-the_kirghiz_light__cd_1-09-meridia_closes-233-262-10.0.wav differ diff --git a/audio/se_samples/enhanced/se_aishell_BAC009S0901W0447-FSD50K_eval_audio_16k_235964-10.0.wav b/audio/se_samples/enhanced/se_aishell_BAC009S0901W0447-FSD50K_eval_audio_16k_235964-10.0.wav new file mode 100644 index 0000000..c5c83ea Binary files /dev/null and b/audio/se_samples/enhanced/se_aishell_BAC009S0901W0447-FSD50K_eval_audio_16k_235964-10.0.wav differ diff --git a/audio/se_samples/enhanced/se_aishell_BAC009S0915W0347-FSD50K_eval_audio_16k_234044-5.0.wav b/audio/se_samples/enhanced/se_aishell_BAC009S0915W0347-FSD50K_eval_audio_16k_234044-5.0.wav new file mode 100644 index 0000000..7693286 Binary files /dev/null and b/audio/se_samples/enhanced/se_aishell_BAC009S0915W0347-FSD50K_eval_audio_16k_234044-5.0.wav differ diff --git a/audio/se_samples/enhanced/se_aishell_BAC009S0915W0432-MagnaTagATune_solace-the_gathering_season-10-hujayni-88-117-7.0.wav b/audio/se_samples/enhanced/se_aishell_BAC009S0915W0432-MagnaTagATune_solace-the_gathering_season-10-hujayni-88-117-7.0.wav new file mode 100644 index 0000000..9325d18 Binary files /dev/null and b/audio/se_samples/enhanced/se_aishell_BAC009S0915W0432-MagnaTagATune_solace-the_gathering_season-10-hujayni-88-117-7.0.wav differ diff --git a/audio/se_samples/enhanced/se_aishell_BAC009S0916W0211-FSD50K_eval_audio_16k_360680-12.0.wav b/audio/se_samples/enhanced/se_aishell_BAC009S0916W0211-FSD50K_eval_audio_16k_360680-12.0.wav new file mode 100644 index 0000000..6e1c609 Binary files /dev/null and b/audio/se_samples/enhanced/se_aishell_BAC009S0916W0211-FSD50K_eval_audio_16k_360680-12.0.wav differ diff --git a/audio/se_samples/enhanced/se_librispeech_1320-122617-0013-FSD50K_eval_audio_16k_325526-5.0.wav b/audio/se_samples/enhanced/se_librispeech_1320-122617-0013-FSD50K_eval_audio_16k_325526-5.0.wav new file mode 100644 index 0000000..66c8950 Binary files /dev/null and b/audio/se_samples/enhanced/se_librispeech_1320-122617-0013-FSD50K_eval_audio_16k_325526-5.0.wav differ diff --git a/audio/se_samples/enhanced/se_librispeech_1998-15444-0019-FSD50K_eval_audio_16k_382586-7.0.wav b/audio/se_samples/enhanced/se_librispeech_1998-15444-0019-FSD50K_eval_audio_16k_382586-7.0.wav new file mode 100644 index 0000000..30bb1aa Binary files /dev/null and b/audio/se_samples/enhanced/se_librispeech_1998-15444-0019-FSD50K_eval_audio_16k_382586-7.0.wav differ diff --git a/audio/se_samples/enhanced/se_librispeech_237-134500-0000-FSD50K_eval_audio_16k_403295-10.0.wav b/audio/se_samples/enhanced/se_librispeech_237-134500-0000-FSD50K_eval_audio_16k_403295-10.0.wav new file mode 100644 index 0000000..94ba2ce Binary files /dev/null and b/audio/se_samples/enhanced/se_librispeech_237-134500-0000-FSD50K_eval_audio_16k_403295-10.0.wav differ diff --git a/audio/se_samples/enhanced/se_librispeech_2414-159411-0013-FSD50K_eval_audio_16k_164036-12.0.wav b/audio/se_samples/enhanced/se_librispeech_2414-159411-0013-FSD50K_eval_audio_16k_164036-12.0.wav new file mode 100644 index 0000000..4a5ae7c Binary files /dev/null and b/audio/se_samples/enhanced/se_librispeech_2414-159411-0013-FSD50K_eval_audio_16k_164036-12.0.wav differ diff --git a/audio/se_samples/enhanced/se_librispeech_260-123440-0011-FSD50K_eval_audio_16k_203808-12.0.wav b/audio/se_samples/enhanced/se_librispeech_260-123440-0011-FSD50K_eval_audio_16k_203808-12.0.wav new file mode 100644 index 0000000..ce4974b Binary files /dev/null and b/audio/se_samples/enhanced/se_librispeech_260-123440-0011-FSD50K_eval_audio_16k_203808-12.0.wav differ diff --git a/audio/se_samples/enhanced/se_librispeech_3538-142836-0003-FSD50K_eval_audio_16k_176925-10.0.wav b/audio/se_samples/enhanced/se_librispeech_3538-142836-0003-FSD50K_eval_audio_16k_176925-10.0.wav new file mode 100644 index 0000000..ac2226e Binary files /dev/null and b/audio/se_samples/enhanced/se_librispeech_3538-142836-0003-FSD50K_eval_audio_16k_176925-10.0.wav differ diff --git a/audio/se_samples/enhanced/se_librispeech_6829-68771-0002-FSD50K_eval_audio_16k_62952-5.0.wav b/audio/se_samples/enhanced/se_librispeech_6829-68771-0002-FSD50K_eval_audio_16k_62952-5.0.wav new file mode 100644 index 0000000..a1b9a21 Binary files /dev/null and b/audio/se_samples/enhanced/se_librispeech_6829-68771-0002-FSD50K_eval_audio_16k_62952-5.0.wav differ diff --git a/audio/se_samples/enhanced/se_librispeech_7105-2330-0027-FSD50K_eval_audio_16k_251931-2.0.wav b/audio/se_samples/enhanced/se_librispeech_7105-2330-0027-FSD50K_eval_audio_16k_251931-2.0.wav new file mode 100644 index 0000000..3a7c3d3 Binary files /dev/null and b/audio/se_samples/enhanced/se_librispeech_7105-2330-0027-FSD50K_eval_audio_16k_251931-2.0.wav differ diff --git a/audio/se_samples/enhanced/se_librispeech_7975-280085-0005-FSD50K_eval_audio_16k_180338-10.0.wav b/audio/se_samples/enhanced/se_librispeech_7975-280085-0005-FSD50K_eval_audio_16k_180338-10.0.wav new file mode 100644 index 0000000..7e65085 Binary files /dev/null and b/audio/se_samples/enhanced/se_librispeech_7975-280085-0005-FSD50K_eval_audio_16k_180338-10.0.wav differ diff --git a/audio/se_samples/enhanced/se_librispeech_8188-269290-0023-FSD50K_eval_audio_16k_337937-7.0.wav b/audio/se_samples/enhanced/se_librispeech_8188-269290-0023-FSD50K_eval_audio_16k_337937-7.0.wav new file mode 100644 index 0000000..ce06fab Binary files /dev/null and b/audio/se_samples/enhanced/se_librispeech_8188-269290-0023-FSD50K_eval_audio_16k_337937-7.0.wav differ diff --git a/audio/se_samples/librispeech.scp b/audio/se_samples/librispeech.scp new file mode 100644 index 0000000..43c595e --- /dev/null +++ b/audio/se_samples/librispeech.scp @@ -0,0 +1,10 @@ +se_librispeech_7105-2330-0027-FSD50K_eval_audio_16k_251931-2.0.wav 3.7330 +se_librispeech_7975-280085-0005-FSD50K_eval_audio_16k_180338-10.0.wav 3.1550 +se_librispeech_6829-68771-0002-FSD50K_eval_audio_16k_62952-5.0.wav 3.5491 +se_librispeech_1320-122617-0013-FSD50K_eval_audio_16k_325526-5.0.wav 3.4878 +se_librispeech_8188-269290-0023-FSD50K_eval_audio_16k_337937-7.0.wav 3.7161 +se_librispeech_1998-15444-0019-FSD50K_eval_audio_16k_382586-7.0.wav 3.2770 +se_librispeech_3538-142836-0003-FSD50K_eval_audio_16k_176925-10.0.wav 3.5454 +se_librispeech_237-134500-0000-FSD50K_eval_audio_16k_403295-10.0.wav 4.0593 +se_librispeech_260-123440-0011-FSD50K_eval_audio_16k_203808-12.0.wav 3.4448 +se_librispeech_2414-159411-0013-FSD50K_eval_audio_16k_164036-12.0.wav 3.4867 diff --git a/audio/se_samples/noisy/se_aishell_BAC009S0764W0445-FSD50K_eval_audio_16k_404398-7.0.wav b/audio/se_samples/noisy/se_aishell_BAC009S0764W0445-FSD50K_eval_audio_16k_404398-7.0.wav new file mode 100644 index 0000000..c12e99d Binary files /dev/null and b/audio/se_samples/noisy/se_aishell_BAC009S0764W0445-FSD50K_eval_audio_16k_404398-7.0.wav differ diff --git a/audio/se_samples/noisy/se_aishell_BAC009S0766W0130-FSD50K_eval_audio_16k_408627-5.0.wav b/audio/se_samples/noisy/se_aishell_BAC009S0766W0130-FSD50K_eval_audio_16k_408627-5.0.wav new file mode 100644 index 0000000..8aaf8fa Binary files /dev/null and b/audio/se_samples/noisy/se_aishell_BAC009S0766W0130-FSD50K_eval_audio_16k_408627-5.0.wav differ diff --git a/audio/se_samples/noisy/se_aishell_BAC009S0768W0436-FSD50K_eval_audio_16k_114454-2.0.wav b/audio/se_samples/noisy/se_aishell_BAC009S0768W0436-FSD50K_eval_audio_16k_114454-2.0.wav new file mode 100644 index 0000000..98d5e16 Binary files /dev/null and b/audio/se_samples/noisy/se_aishell_BAC009S0768W0436-FSD50K_eval_audio_16k_114454-2.0.wav differ diff --git a/audio/se_samples/noisy/se_aishell_BAC009S0770W0460-musan_noise-free-sound-0731-2.0.wav b/audio/se_samples/noisy/se_aishell_BAC009S0770W0460-musan_noise-free-sound-0731-2.0.wav new file mode 100644 index 0000000..2046698 Binary files /dev/null and b/audio/se_samples/noisy/se_aishell_BAC009S0770W0460-musan_noise-free-sound-0731-2.0.wav differ diff --git a/audio/se_samples/noisy/se_aishell_BAC009S0901W0350-FSD50K_eval_audio_16k_67307-12.0.wav b/audio/se_samples/noisy/se_aishell_BAC009S0901W0350-FSD50K_eval_audio_16k_67307-12.0.wav new file mode 100644 index 0000000..ca6fab9 Binary files /dev/null and b/audio/se_samples/noisy/se_aishell_BAC009S0901W0350-FSD50K_eval_audio_16k_67307-12.0.wav differ diff --git a/audio/se_samples/noisy/se_aishell_BAC009S0901W0443-MagnaTagATune_rapoon-the_kirghiz_light__cd_1-09-meridia_closes-233-262-10.0.wav b/audio/se_samples/noisy/se_aishell_BAC009S0901W0443-MagnaTagATune_rapoon-the_kirghiz_light__cd_1-09-meridia_closes-233-262-10.0.wav new file mode 100644 index 0000000..4ee1c5f Binary files /dev/null and b/audio/se_samples/noisy/se_aishell_BAC009S0901W0443-MagnaTagATune_rapoon-the_kirghiz_light__cd_1-09-meridia_closes-233-262-10.0.wav differ diff --git a/audio/se_samples/noisy/se_aishell_BAC009S0901W0447-FSD50K_eval_audio_16k_235964-10.0.wav b/audio/se_samples/noisy/se_aishell_BAC009S0901W0447-FSD50K_eval_audio_16k_235964-10.0.wav new file mode 100644 index 0000000..cf123b0 Binary files /dev/null and b/audio/se_samples/noisy/se_aishell_BAC009S0901W0447-FSD50K_eval_audio_16k_235964-10.0.wav differ diff --git a/audio/se_samples/noisy/se_aishell_BAC009S0915W0347-FSD50K_eval_audio_16k_234044-5.0.wav b/audio/se_samples/noisy/se_aishell_BAC009S0915W0347-FSD50K_eval_audio_16k_234044-5.0.wav new file mode 100644 index 0000000..146fa04 Binary files /dev/null and b/audio/se_samples/noisy/se_aishell_BAC009S0915W0347-FSD50K_eval_audio_16k_234044-5.0.wav differ diff --git a/audio/se_samples/noisy/se_aishell_BAC009S0915W0432-MagnaTagATune_solace-the_gathering_season-10-hujayni-88-117-7.0.wav b/audio/se_samples/noisy/se_aishell_BAC009S0915W0432-MagnaTagATune_solace-the_gathering_season-10-hujayni-88-117-7.0.wav new file mode 100644 index 0000000..6223721 Binary files /dev/null and b/audio/se_samples/noisy/se_aishell_BAC009S0915W0432-MagnaTagATune_solace-the_gathering_season-10-hujayni-88-117-7.0.wav differ diff --git a/audio/se_samples/noisy/se_aishell_BAC009S0916W0211-FSD50K_eval_audio_16k_360680-12.0.wav b/audio/se_samples/noisy/se_aishell_BAC009S0916W0211-FSD50K_eval_audio_16k_360680-12.0.wav new file mode 100644 index 0000000..d03c2e4 Binary files /dev/null and b/audio/se_samples/noisy/se_aishell_BAC009S0916W0211-FSD50K_eval_audio_16k_360680-12.0.wav differ diff --git a/audio/se_samples/noisy/se_librispeech_1320-122617-0013-FSD50K_eval_audio_16k_325526-5.0.wav b/audio/se_samples/noisy/se_librispeech_1320-122617-0013-FSD50K_eval_audio_16k_325526-5.0.wav new file mode 100644 index 0000000..4a66451 Binary files /dev/null and b/audio/se_samples/noisy/se_librispeech_1320-122617-0013-FSD50K_eval_audio_16k_325526-5.0.wav differ diff --git a/audio/se_samples/noisy/se_librispeech_1998-15444-0019-FSD50K_eval_audio_16k_382586-7.0.wav b/audio/se_samples/noisy/se_librispeech_1998-15444-0019-FSD50K_eval_audio_16k_382586-7.0.wav new file mode 100644 index 0000000..77f0206 Binary files /dev/null and b/audio/se_samples/noisy/se_librispeech_1998-15444-0019-FSD50K_eval_audio_16k_382586-7.0.wav differ diff --git a/audio/se_samples/noisy/se_librispeech_237-134500-0000-FSD50K_eval_audio_16k_403295-10.0.wav b/audio/se_samples/noisy/se_librispeech_237-134500-0000-FSD50K_eval_audio_16k_403295-10.0.wav new file mode 100644 index 0000000..7291d2d Binary files /dev/null and b/audio/se_samples/noisy/se_librispeech_237-134500-0000-FSD50K_eval_audio_16k_403295-10.0.wav differ diff --git a/audio/se_samples/noisy/se_librispeech_2414-159411-0013-FSD50K_eval_audio_16k_164036-12.0.wav b/audio/se_samples/noisy/se_librispeech_2414-159411-0013-FSD50K_eval_audio_16k_164036-12.0.wav new file mode 100644 index 0000000..b00c957 Binary files /dev/null and b/audio/se_samples/noisy/se_librispeech_2414-159411-0013-FSD50K_eval_audio_16k_164036-12.0.wav differ diff --git a/audio/se_samples/noisy/se_librispeech_260-123440-0011-FSD50K_eval_audio_16k_203808-12.0.wav b/audio/se_samples/noisy/se_librispeech_260-123440-0011-FSD50K_eval_audio_16k_203808-12.0.wav new file mode 100644 index 0000000..2cd95aa Binary files /dev/null and b/audio/se_samples/noisy/se_librispeech_260-123440-0011-FSD50K_eval_audio_16k_203808-12.0.wav differ diff --git a/audio/se_samples/noisy/se_librispeech_3538-142836-0003-FSD50K_eval_audio_16k_176925-10.0.wav b/audio/se_samples/noisy/se_librispeech_3538-142836-0003-FSD50K_eval_audio_16k_176925-10.0.wav new file mode 100644 index 0000000..8769bb4 Binary files /dev/null and b/audio/se_samples/noisy/se_librispeech_3538-142836-0003-FSD50K_eval_audio_16k_176925-10.0.wav differ diff --git a/audio/se_samples/noisy/se_librispeech_6829-68771-0002-FSD50K_eval_audio_16k_62952-5.0.wav b/audio/se_samples/noisy/se_librispeech_6829-68771-0002-FSD50K_eval_audio_16k_62952-5.0.wav new file mode 100644 index 0000000..9f59786 Binary files /dev/null and b/audio/se_samples/noisy/se_librispeech_6829-68771-0002-FSD50K_eval_audio_16k_62952-5.0.wav differ diff --git a/audio/se_samples/noisy/se_librispeech_7105-2330-0027-FSD50K_eval_audio_16k_251931-2.0.wav b/audio/se_samples/noisy/se_librispeech_7105-2330-0027-FSD50K_eval_audio_16k_251931-2.0.wav new file mode 100644 index 0000000..0947ebb Binary files /dev/null and b/audio/se_samples/noisy/se_librispeech_7105-2330-0027-FSD50K_eval_audio_16k_251931-2.0.wav differ diff --git a/audio/se_samples/noisy/se_librispeech_7975-280085-0005-FSD50K_eval_audio_16k_180338-10.0.wav b/audio/se_samples/noisy/se_librispeech_7975-280085-0005-FSD50K_eval_audio_16k_180338-10.0.wav new file mode 100644 index 0000000..332437b Binary files /dev/null and b/audio/se_samples/noisy/se_librispeech_7975-280085-0005-FSD50K_eval_audio_16k_180338-10.0.wav differ diff --git a/audio/se_samples/noisy/se_librispeech_8188-269290-0023-FSD50K_eval_audio_16k_337937-7.0.wav b/audio/se_samples/noisy/se_librispeech_8188-269290-0023-FSD50K_eval_audio_16k_337937-7.0.wav new file mode 100644 index 0000000..d3c0ee1 Binary files /dev/null and b/audio/se_samples/noisy/se_librispeech_8188-269290-0023-FSD50K_eval_audio_16k_337937-7.0.wav differ diff --git a/index.html b/index.html index e950ead..9484fc7 100644 --- a/index.html +++ b/index.html @@ -71,7 +71,7 @@

LauraGPT

-
+
@@ -237,7 +237,73 @@

Demos

-

1. Automatic speech recognition (ASR) samples

+ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +

3. Speech to text translation (S2TT) samples


@@ -251,81 +317,77 @@

1. Automatic speech recognition (ASR) samples

+ + - -
-

i always accept the gift, after deprecating the - honour with words and gestures, and a little later, - in accordance with what i believe to be the modern - practice, return the compliment.

+

But not all of them can be successful in the market.

+ +
-
+ +

Welcome to the advanced course on the UNIT dialogue system.

+ -

2. Text-to-speech synthesis (TTS) samples

-
-
- - - - - - - - + + + + + + - + - -
Prompt textTextPrompt Speech + Synthesis Speech
- later in accordance with what i believe to be the modern practice + -

i always accept the gift, after deprecating the - honour with words and gestures, and a little later, - in accordance with what i believe to be the modern - practice, return the compliment.

+

Then, upload the AR content package to the AR content platform.

+

但他似乎没有意识到任何危险。

+
-
+ -

3. Speech to text translation (S2TT) samples

-
-
- - - - + + + + - - + @@ -352,146 +414,186 @@

4. Speech enhancement (SE) samples

- - -
Original speechTranscribed Text + + +

我想预订一间靠近我们公寓的酒吧。

+
-

i always accept the gift, after deprecating the - honour with words and gestures, and a little later, - in accordance with what i believe to be the modern - practice, return the compliment.

+

主要是那些努力实现自己命运的人的心。

-
- -

5. Automated audio captioning (AAC) samples

-
-
- - - - - - - - - - - - -
Original speechTranscribed Text
-

i always accept the gift, after deprecating the - honour with words and gestures, and a little later, - in accordance with what i believe to be the modern - practice, return the compliment.

+
-
- -

6. Speech emotion recognition (SER) samples

-
-
- - - - - - - - - - - -
Original speechTranscribed Text
-

i always accept the gift, after deprecating the - honour with words and gestures, and a little later, - in accordance with what i believe to be the modern - practice, return the compliment.

+
-
- -

7. Spoken language understanding (SLU) samples

-
-
- - - - - - - - - -
Original speechTranscribed Text
-

i always accept the gift, after deprecating the - honour with words and gestures, and a little later, - in accordance with what i believe to be the modern - practice, return the compliment.

+
-

8. Machine translation (MT) samples

-
-
- - - - - - - - - - - + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + - + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + - -
Prompt textText
- later in accordance with what i believe to be the modern practice - -

i always accept the gift, after deprecating the - honour with words and gestures, and a little later, - in accordance with what i believe to be the modern - practice, return the compliment.

-
-
+ + + + + + + + + + + + + + + + + + + + + + + + + + + +
diff --git a/style.css b/style.css index 08d7812..4281183 100644 --- a/style.css +++ b/style.css @@ -339,6 +339,7 @@ a:hover, a:active { .hero-content { background: url("images/lauragpt.png") no-repeat center; background-size: cover; + background-color: white; } .hero-content-overlay {